Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the HeiChole benchmark.

PURPOSE: Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase the safety of the operation through context-sensitive warnings and semi-autonomous robotic assistance or improve training of surgeons via data-driven feedback. In surgical workflow analysis up to 91% average precision has been reported for phase recognition on an open data single-center video dataset. In this work we investigated the generalizability of phase recognition algorithms in a multicenter setting including more difficult recognition tasks such as surgical action and surgical skill. METHODS: To achieve this goal, a dataset with 33 laparoscopic cholecystectomy videos from three surgical centers with a total operation time of 22 h was created. Labels included framewise annotation of seven surgical phases with 250 phase transitions, 5514 occurences of four surgical actions, 6980 occurences of 21 surgical instruments from seven instrument categories and 495 skill classifications in five skill dimensions. The dataset was used in the 2019 international Endoscopic Vision challenge, sub-challenge for surgical workflow and skill analysis. Here, 12 research teams trained and submitted their machine learning algorithms for recognition of phase, action, instrument and/or skill assessment. RESULTS: F1-scores were achieved for phase recognition between 23.9% and 67.7% (n = 9 teams), for instrument presence detection between 38.5% and 63.8% (n = 8 teams), but for action recognition only between 21.8% and 23.3% (n = 5 teams). The average absolute error for skill assessment was 0.78 (n = 1 team). CONCLUSION: Surgical workflow and skill analysis are promising technologies to support the surgical team, but there is still room for improvement, as shown by our comparison of machine learning algorithms. This novel HeiChole benchmark can be used for comparable evaluation and validation of future work. In future studies, it is of utmost importance to create more open, high-quality datasets in order to allow the development of artificial intelligence and cognitive robotics in surgery.

Comparative validation of multi-instance instrument segmentation in endoscopy: Results of the ROBUST-MIS 2019 challenge.

Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions. In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).

Urinary Imaging Findings in Young Infants With Bacteremic Urinary Tract Infection.

OBJECTIVES: To describe renal ultrasound (RUS) and voiding cystourethrogram (VCUG) findings and determine predictors of abnormal imaging in young infants with bacteremic urinary tract infection (UTI). METHODS: We used retrospective data from a multicenter sample of infants younger than 3 months with bacteremic UTI, defined as the same pathogenic organism in blood and urine. Infants were excluded if they had any major comorbidities, known urologic abnormalities at time of presentation, required intensive unit care, or had no imaging performed. Imaging results as stated in the radiology reports were categorized by a pediatric urologist. RESULTS: Of the 276 infants, 19 were excluded. Of the remaining 257 infants, 254 underwent a RUS and 224 underwent a VCUG. Fifty-five percent had ≥1 RUS abnormalities. Thirty-four percent had ≥1 VCUG abnormalities, including vesicoureteral reflux (VUR, 27%), duplication (1.3%), and infravesicular abnormality (0.9%). Age <1 month, male sex, and non-Escherichia coli organism predicted an abnormal RUS, but only non-E coli organism predicted an abnormal VCUG. Seventeen of 96 infants (17.7%) with a normal RUS had an abnormal VCUG: 15 with VUR (Grade I-III = 13, Grade IV = 2), 2 with elevated postvoid residual, and 1 with infravesical abnormality. CONCLUSIONS: Although RUS and VCUG abnormalities were common in this cohort, the frequency and severity were similar to previous studies of infants with UTIs in general. Our findings do not support special consideration of bacteremia in imaging decisions for otherwise well-appearing young infants with UTI.

Intravenous delivery of cysteamine for the treatment of cystinosis: association with hepatotoxicity.

Nephropathic cystinosis is a lysosomal storage disorder, which, if untreated, results in renal failure by age 10 years. Oral cysteamine has been shown to preserve renal function in these patients. In this study, a 2-year-old girl with nephropathic cystinosis and severe gastrointestinal dysmotility was treated with intravenous (i.v.) administration of cysteamine hydrochloride (HCl). This is only the second report of long-term i.v. cysteamine therapy for nephropathic cystinosis. Unlike the treatment in the previous case, however, treatment in our patient was limited by liver toxicity.