This is the second study demonstrating the VETSCAN IMAGYST system integrated with a deep learning object detection algorithm successfully recognized and identified diagnostic forms of gastrointestinal parasites in dogs and cats on fecal flotation slides scanned by an automated microscope. Whereas our previous study evaluated the VETSCAN IMAGYST system in detecting eggs of Ancylostoma, Toxocara, Trichuris, and Taeniidae in 84 canine and 16 feline fecal samples [40], this study assessed the ability of the system to detect eggs of feline nematodes, Ancylostoma and Toxocara cati, and protozoan parasites, Cystoisospora oocysts and Giardia cysts, in 104 canine and 96 feline fecal samples, making it the more comprehensive analysis for this novel system.
Although both domestic dogs (Canis lupus familiaris) and cats (Felis catus) belong to the same order of Carnivora, dogs are classified into the Canoidea superfamily and cats are classified into the Feloidea superfamily [46, 47]. Diets of Canoids can be variable from herbivorous to omnivorous; however, all Feloids require a strict carnivorous diet [47]. Therefore, a high-protein diet is essential for domestic cats to obtain some nutritional requirements of animal-origin, such as taurine, arachidonic acid, and vitamin A [47]. Due to the differences in dietary requirements, feline fecal samples commonly contain a large amount of fat and become soft, sticky and clay-like in consistency, which often makes it more difficult, or sometimes impossible, to read fecal slides since more debris float with fats, especially when a viscous sugar solution is used as the centrifugal flotation technique. Modification of fecal flotation procedures, involving an initial water wash where the supernatant is discarded after the initial spin and the sediment resuspended with a flotation solution to remove excess fat, mucus, and debris (double centrifugal fecal flotation technique), can be used [10]. In the current study, the VETSCAN IMAGYST centrifugal flotation method recovered parasite elements from feline feces, and the VETSCAN IMAGYST scanner and algorithm successfully captured and identified targeted parasites (Figure 5).
This is the first report demonstrating the ability of the VETSCAN IMAGYST system to recover and accurately detect protozoan parasites, Cystoisospora oocysts and Giardia cysts. Although coccidiosis is generally considered a self-limiting infection in mature dogs and cats due to rapid development of immunity [18], Cystoisospora is an ubiquitous and important pathogen in puppies and kittens, often resulting in diarrhea, abdominal pain, anorexia, bloody diarrhea, anemia, and even mortality in severe cases [10, 17, 48]. Since Cystoisospora undergoes fast replication in the pathogenic intestinal stage and excrete a high number of oocysts in feces, causing environmental contamination, it is critical and recommended to conduct a fecal examination with centrifugation for puppies and kittens at least four times during the first year of life and treat at an early stage of infection [48, 49]. Two different species of Cystoisospora are commonly diagnosed in dogs and cats: C. canis and C. ohioensis in dogs and C. felis and C. rivolta in cats. Oocysts of C. canis and C. felis are slightly bigger, approximately 38-51 x 27-39 µm in size, than those of C. ohioensis and C. rivolta, approximately 17-27 x 15-24 µm in size [10]. Due to the smaller size of coccidian oocysts compared to helminth eggs, Cystoisospora can be easily overlooked especially when a low number of oocysts are on a fecal slide and an inaccurate microscopic focus is used for examination. The VETSCAN IMAGYST system correctly identified oocysts of all four Cystoisospora species in canine and feline fecal samples and successfully reported as Cystoisospora (coccidia) (Figure 5).
The diagnostic sensitivity and specificity comparing the results of Giardia samples reported by experts versus by the VETSCAN IMAGYST scanner and algorithm were 75.8% and 97.0%, respectively (Table 2). As previously discussed, a common challenge for many object detection algorithm models is to precisely localize and distinguish small objects such as Giardia cysts [40]. With the nature of a deep learning algorithm, however, performance continues improving with further trainings. It is important to note that the diagnostic sensitivity dramatically increased to 95.2% by removing the 12 of 33 Giardia samples with ≤10 CPG, which is extremely demanding to detect by a visual microscopic examination, from the analysis. Additionally, examinations and counts of CPG on these Giardia slides were carefully performed by a well-trained diagnostic parasitologist with no time limit, which most likely resulted in a much higher diagnostic performance compared to performance by technicians in daily veterinary practices.
Detection of Giardia cysts and trophozoites by fecal examinations is generally the most sensitive microscopic technique, and ample trainings and experiences are required to confidently diagnose giardiasis [10]. In addition to its small size and transparency in color, it is challenging to identify Giardia infection by fecal examinations because Giardia cysts and trophozoites are intermittently shed in feces, and multiple fecal examinations may be necessary to rule out the infection. Fresh fecal samples, preferably within 30 minutes of defecation, are often required to detect motile trophozoites; and Giardia cysts and trophozoites are fairly fragile and easily distorted by flotation solutions [10]. A 33% zinc sulfate solution (specific gravity, 1.18) is preferred and recommended for the detection of Giardia cysts as other flotation solutions can rapidly cause osmotic damages in Giardia cysts, which increases the difficulty in perceiving them on fecal slides [10, 34, 50, 51]. During the current study, the VETSCAN IMAGYST system effectively recognized and identified both intact and collapsed Giardia cysts (Figure 5). Testing for Giardia is recommended not only in symptomatic dogs and cats, but also in new dogs and cats being introduced to home with other pets free of infection, as many Giardia infections can be asymptomatic [10, 32, 48]. Since there is no perfect flotation solution to recover all different types of parasites [10], it is important to consider advantages and disadvantage of each solution when selecting one for general use. Some experts recommend performing two centrifugal flotation tests using both Sheather’s sugar and 33% zinc sulfate solutions to have a broader range of gastrointestinal parasite detections. In cases where Giardia is suspected, an analysis with the sugar flotation solution should also be performed on the fecal sample to assess for other parasites.
Detection of Giardia is also possible with Giardia-specific coproantigen detection assays [35, 48]. However, when not used in conjunction with a traditional microscopic technique, antigen testing may provide a false positive result in an animal that is no longer infected with Giardia due to persistent antigen excretion for several weeks or even months after the parasite elimination [52, 53]. Given the shortcomings of current in-house diagnostic methods for Giardia, utilizing a deep learning algorithm platform, such as the VETSCAN IMAGYST system, could provide clinicians with an excellent additional or alternative diagnostic tool to help identify Giardia cases that would otherwise be missed.
Evaluation of the performance of the VETSCAN IMAGYST centrifugal flotation sample preparation method was limited due to modest numbers of true positives for the four targeted parasites in this study and the inherent subsampling variability in non-homogenous fecal samples that has been well documented in previous publications [54]. Kochanowski et al. [54] observed a wide range of coefficients of variation between 31-254% in Toxocara and Trichuris samples with a low number of egg counts of ≤50 EPG. Despite these limitations, the performance of the VETSCAN IMAGYST centrifugal flotation method was comparable to a conventional centrifugal flotation method, with diagnostic sensitivity and specificity of the comparisons ranging between 65.7-100% and 97.6-100%, respectively, across the four targeted parasites (Table 3). Additionally, one potential modification considered for the VETSCAN IMAGYST centrifugal flotation method to increase the diagnostic sensitivity is to lengthen the duration of centrifugation time. Previous studies reported that egg recoveries with centrifugation for 4 or 5 minutes at 264 x g improved significantly compared to 1 and 3 minutes at the same speed, although no change was observed in egg recoveries by extending times to 10 or 20 minutes [37, 55].
As shown in Table 3, the diagnostic sensitivity and specificity of the VETSCAN IMAGYST centrifugal technique slightly surpassed those of the OVASSAY® passive flotation method. Despite the fact that centrifugation significantly increases the sensitivity of fecal examinations, passive flotation continues to be the most commonly used technique in veterinary private practices due to its convenience [10, 19, 36, 51, 56-58]. Given that the VETSCAN IMAGYST system reliably recovers and detects parasite elements in fecal samples, does not depend considerably on the experience level of examiners, and has previously been shown to provide results in around 10 minutes with the VETSCAN IMAGYST centrifugal flotation method [40], it has the potential to replace the conventional passive flotation method performed in veterinary practices.
The most distinctive and unique feature of the VETSCAN IMAGYST system is its deep learning object detection algorithm. To the best of our knowledge, the VETSCAN IMAGYST system is the only automated diagnostic system that is integrated with a deep learning object detection algorithm and applied in veterinary medicine. Compared to shallow learning systems, which do not have any structural information on the function to be learned, deep learning algorithms exploit the advantage of locality at each level of the layered hierarchy, enabling the system to ignore the aspects that make computer vision brittle [59, 60]. Layered hierarchy also facilitates the system to continuously adapt to new data and apply it to new output classes with fewer examples [60, 61]. The deep learning characteristic, along with the YOLOv3 object detection model [43], which incorporates localization and classification features, results in a decrease of background errors and high agreement between the VETSCAN IMAGYST system and experts’ examinations. Another benefit of this system is the ability to store images and reports on a secure, cloud-based server system, allowing easy sharing by parasitologists as well as members of the veterinary and academic communities for patient care, research, and teaching.
The current study did not evaluate the usability of the system; however, our previous analysis showed that the VETSCAN IMAGYST system with the VETSCAN IMAGYST centrifugal flotation method could prepare examination results in around 10 minutes, which is comparable to conventional fecal flotation tests. This time frame included the time to prepare the sample, approximately 3.5 minutes with 2-minute centrifugal incubation time, and the time to scan the images, approximately 6-7 minutes [40]. Data from the current study add to the body of evidence demonstrating the performance of the VETSCAN IMAGYST system in detecting intestinal parasite elements recovered from fecal samples. In addition to identifying the protozoan parasites, Cystoisospora and Giardia, results from our current and previous studies show the system’s reliable performance in detecting four different genera/group of gastrointestinal parasites (Ancylostoma, Toxocara, Trichuris, Taeniidae) in dogs and cats [40]. With further traning, the VETSCAN IMAGYST system will have the ability to identify other parasites. The quantitative capability of the VESTSCAN IMAGYST system is currently under development. It is predicted that the algorithm will be able to perform a fecal egg counting test.