Hata, Jane

Abstract Background Gram stain (GS) is essential for preliminary bacterial identification. The lack of a standardized quality control method for GS is a significant drawback. By utilizing a deep convolutional neural network (CNN) design, we present a proof-of-concept for a novel solution to GS quality assurance. Using this approach, current manual GS, and potentially automated GS methods, may possess a standardized method of quality control. Methods Twenty-nine GS from positive blood cultures encompassing the spectrum of GS quality (acceptable, over/under decolorization, smear thickness, stain artifact) were selected by two expert microbiologists. A total of 197 images were obtained using a Cognex D-900 camera and Olympus BX-43 microscope at 1000X magnification. Images were classified using deep learning software (Cognex, ViDi Suite 4.1). Eighty-one images were classified as suboptimal and 116 were classified as optimal by expert review. To address background variation due to manual GS, we implemented a screening classification tool to separate images into 5 distinct classes (pale, rose, orange, indigo, variegated). The training and test sets consisted of 100 and 97 images respectively. Using a chaining technique, a second classification tool was added after the screening classification tool. The second tool further divided the 197 images into two dataset classes: optimal and suboptimal. The second tool used 105 images for training and 92 images for the test set. Model performance was compared to expert microbiology review, with GS verified by organism identification using MALDI-TOF. Results Cognex ViDi Suite 4.1 could discriminate between optimal and suboptimal GS images. The chained classification tool was able to be trained with 100% recall and 100% accuracy, with a resulting F-score of 1.00. Figure 1 VisionPro GUI with optimal image (MRSA) Conclusion Deep learning enabled image analysis is an effective method for sorting GS which are acceptable for further interpretation and suboptimal smears which require rework. Additional study is warranted to develop deep learning image analysis tools for the interpretation of GS on multiple specimen types and incorporate into automated GS systems. Disclosures Jane Hata, PhD , D(ABMM), Roche Molecular Systems: Grant/Research Support Kyle Magee, MLS(ASCP), SeluxDx: Employee

Abstract Background Echinococcus multilocularis is a destructive zoonotic cestode with low human incidence. Hydatid disease classically presents with hepatic or lung involvement with infrequent extrahepatic bone destruction. Diagnosis is challenging due to its latency and mimicry. Fig.1: Case 1 - X-ray imaging of the pelvis shows osseous destruction of the iliac crest secondary to known osteomyelitis status post left ilium debridement. Fig.2: Case 1 - Magnetic resonance imaging demonstrates extensive osteomyelitis throughout left ilium. Stable scattered focal fluid collections seen throughout the left lower quadrant. Methods CASE 1: A 57 year-old Albanian male with diabetes, latent TB, and left iliac lytic lesion presented with 4 weeks of left flank pain and was treated with 6 weeks of IV Ceftriaxone and Flagyl. 2 years later he returned with flank pain and purulent lumbar drainage. Hip x-ray suggested chronic osteomyelitis, with left psoas fluid collections on CT. Bartonella, Q fever, Brucella, HIV, AFB and fungal serologies were negative. Hemipelvis debridement revealed structures concerning for hydatid disease. Echinococcus IgG was equivocal. Histopathology was consistent with Echinococcus multilocularis species, and albendazole was started. On follow-up, he presented with left hip tenderness and toe extensor weakness. Labs showed mild leukocytosis. CT revealed progressive destruction of the left iliac with sacroiliac extension concerning for abscess. CASE 2: A 36 year-old female presented with lung and liver cysts, progressive dyspnea, and non-productive cough. She lived in Africa, Asia, and Europe and consumed local street food and unpasteurized milk. Hobbies included spelunking and swimming in freshwater lakes. She had exposure to stray animals, but denied bites or scratches. Over 4 years dyspnea progressed to orthopnea. MR abdomen revealed a 10x6x12cm liver cyst and chest CT showed 2 fluid-attenuating lesions in the LLL and RLL, measuring 4.9 x 6.0 cm and 6.8 x 4.3 cm respectively. Echinococcus, Bartonella, Q fever, Brucella, HIV, AFB and fungal serologies were negative. Schistosomiasis serology was equivocal. Fig. 3: Case 2 - MRI abdomen demonstrating 10x6x12cm liver cyst Fig. 4: Case 2 - Chest CT showed 2 dominant fluid attenuating lesions within the LLL and RLL. The larger lesion in RLL measures 6.8 x 4.3 cm. The left lower lobe lesion measures 4.9 x 6.0 cm. Results Patient 1 underwent type I hemipelvectomy. Patient 2 underwent pulmonary segmentectomy and liver lobectomy. Both were continued on albendazole. Fig. 5: Case 1 - Photo taken during debridement of left ileac and hip. Note presence of white cysts discovered intraoperatively. Fig. 6: Case 1 - Histopathologic slides (H&E stain) demonstrating hooks and scolices consistent with Echinococcus multilocularis. A. Hooklet (100x magnification). B. Hydatid cyst with black-staining structures suggestive of degenerating hooklets. C. Zoomed detail of cyst wall. D. Degenerating hydatid cyst and hooklets. Conclusion Equivocal IgG serology does not exclude infection. History and clinical presentation are key to diagnosis, but histopathology remains the gold standard. Hydatid bone infection progresses insidiously and frequently recurs, depending upon excision and debridement. Finally, echinococcosis demands aggressive long-term therapy and surveillance. Disclosures Claudia R. Libertin, MD, Pfizer, Inc. (Grant/Research Support, Research Grant or Support)