Summary of the National Cancer Institute 2023 Virtual Workshop on Medical Image De-identification-Part 2: Pathology Whole Slide Image De-identification, De-facing, the Role of AI in Image De-identification, and the NCI MIDI Datasets and Pipeline.

De-identification of medical images intended for research is a core requirement for data sharing initiatives, particularly as the demand for data for artificial intelligence (AI) applications grows. The Center for Biomedical Informatics and Information Technology (CBIIT) of the United States National Cancer Institute (NCI) convened a two half-day virtual workshop with the intent of summarizing the state of the art in de-identification technology and processes and exploring interesting aspects of the subject. This paper summarizes the highlights of the second day of the workshop, the recordings and presentations of which are publicly available for review. The topics covered included pathology whole slide image de-identification, de-facing, the role of AI in image de-identification, and the NCI Medical Image De-Identification Initiative (MIDI) datasets and pipeline.

A patient-centric dataset of images and metadata for identifying melanomas using clinical context.

Prior skin image datasets have not addressed patient-level information obtained from multiple skin lesions from the same patient. Though artificial intelligence classification algorithms have achieved expert-level performance in controlled studies examining single images, in practice dermatologists base their judgment holistically from multiple lesions on the same patient. The 2020 SIIM-ISIC Melanoma Classification challenge dataset described herein was constructed to address this discrepancy between prior challenges and clinical practice, providing for each image in the dataset an identifier allowing lesions from the same patient to be mapped to one another. This patient-level contextual information is frequently used by clinicians to diagnose melanoma and is especially useful in ruling out false positives in patients with many atypical nevi. The dataset represents 2,056 patients (20.8% with at least one melanoma, 79.2% with zero melanomas) from three continents with an average of 16 lesions per patient, consisting of 33,126 dermoscopic images and 584 (1.8%) histopathologically confirmed melanomas compared with benign melanoma mimickers.

Preoperative radiographic parameters predict long-term renal impairment following partial nephrectomy.

PURPOSE: We analyzed radiographic parameters describing anatomic features of renal tumors to identify preoperative characteristics that could help predict long-term decline in renal function following partial nephrectomy. METHODS: We retrospectively reviewed the records of 194 consecutive patients who underwent partial nephrectomy from January 2006 to March 2009 and analyzed a cohort of 53 patients for whom complete clinical, radiographic, and operative information was available. Computed tomography images were reviewed by a single radiologist. Radiographic criteria for describing renal tumor size and location included diameter, volume, endophytic properties, proximity to collecting system, anterior/posterior location, location relative to polar lines, and R.E.N.A.L. nephrometry score. Postoperative estimated glomerular filtration rate was calculated using the MDRD study group equation with serum creatinine at last follow-up. RESULTS: The median preoperative and postoperative GFR values were 75 (IQR 65-97) and 66 (IQR 55-84) mL/min/1.73 m(2), respectively. At a median follow-up of 38 months, the median percentage decrease in GFR was 12%. On univariate analyses, tumor diameter (P = 0.002), tumor volume (P < 0.0001), nearness of tumor to collecting system (P = 0.017), and location relative to polar lines (P = 0.017) were associated with percentage decrease in GFR. Furthermore, higher R.E.N.A.L. nephrometry score was also associated with poorer renal functional outcomes following partial nephrectomy (P = 0.019). CONCLUSIONS: Anatomic features of renal tumors defined by preoperative radiographic characteristics correlate with the degree of renal functional decline after partial nephrectomy. Identification of these parameters may assist in patient counseling and clinical decision making following partial nephrectomy. Validation in larger prospective studies is necessary.

Automated framework for digital radiation dose index reporting from CT dose reports.

OBJECTIVE: Radiation exposure from CT studies has increased over the past 30 years in the United States and now constitutes approximately 50% of the radiation dose index administered in the health care setting. Tracking CT dose index (CTDI) is cumbersome because it relies on a manufacturer-generated screen capture, which contains the estimated dose index exposure for the patient. The radiation dose index information is not digital but, rather, is "burned" into the image (i.e., not in numeric form, not as part of the image header or elsewhere associated with the study), making it difficult to automatically share these data with other information systems. The purpose of the dose index reporting application (DIRA) we developed for CT is to extract the radiation dose index information from the CTDI reports to eventually perform automated quality control, promote radiation safety awareness, and provide a longitudinal record of patient-specific health care-related radiation exposure. MATERIALS AND METHODS: A random selection of 518 CTDI reports were processed by the DIRA and the dose index information was extracted. CTDI reports using a standard DICOM C-STORE to the DIRA allow an automated process to compile radiation dose index and patient information in a Web-based framework using a structured query language (SQL) database. RESULTS: Our initial tests showed that the DIRA accurately extracted dose index information from 518 of 518 CTDI reports (100%). Because the extracted CTDI descriptor-dose-length product-is based on standard CTDI measurements obtained using fixed-size cylindric polymethylmethacrylate phantoms, preliminary studies have been performed to correct for patient size by applying correction factors derived from CTDI measurements using a range of phantom sizes from 6 to 32 cm in diameter. Our system provides a way to automatically track CTDI on existing CT scanners and does not rely on the DICOM SR Dose Index Report standard, which is available on only the newest CT scanners. CONCLUSION: A modular and vendor-independent DIRA system can be integrated with any existing CT scanner. This system greatly facilitates digital dose index reporting and makes it possible to provide a longitudinal record of the health care radiation exposure estimate in an individual patient's health record.

Changes in hepatic venous morphology with cirrhosis on MRI.

PURPOSE: To identify changes in vascular morphology on magnetic resonance imaging (MRI) in patients with cirrhosis and to compare these findings to liver donors. MATERIALS AND METHODS: Patients undergoing liver transplantation with biopsy-proven cirrhosis (n = 74) and liver donor candidates (n = 85) underwent dynamic gadolinium-enhanced 3D MR at 1.5T. Vessel diameters were measured independently by three radiologists and features of cirrhosis were identified and correlated with cirrhosis. RESULTS: Hepatic veins were smaller in patients with cirrhosis (4.9, 4.5, and 5.0 mm for right, middle, and left vs. 9.9, 7.6, and 8.9 mm in donors, P << 0.001) and were negatively correlated with cirrhosis (P < 0.001). Right hepatic vein (RHV) <5 mm diagnosed cirrhosis with 59% sensitivity and 99% specificity; the sensitivity and specificity were 88% and 85% for RHV <7 mm. Main portal vein was minimally larger in cirrhosis, 14 versus 12 mm (P < 0.001) in donors. Right portal veins were smaller in cirrhotic patients, 6.5 and 6.2 mm compared to 8.4 and 7.6 mm (P << 0.001), respectively, in donors. CONCLUSION: Vascular features of cirrhosis include small hepatic veins, minimally enlarged main portal vein, and small intrahepatic portal veins; these features may facilitate identification of cirrhosis.

Photon-deficient Mass on FDG-PET Scan in Renal Cell Carcinoma: A Case Report.

F-18 Fluorodeoxyglucose Positron Emission Tomography imaging (F-18 FDG PET) detects malignancies depending on the uptake profile of glycolysis of tumors; however, the role of FDG PET is limited in the evaluation of primary renal malignancy because of low FDG uptake by renal cell carcinoma and also because normal urinary excretion of FDG seen in the images. A patient with renal cell carcinoma whose FDG PET imaging study incidentally shows a photon-deficient mass in the upper pole of the right kidney is present here. The diagnosis is also validated by the histopathological findings of tumor necrosis, hemorrhage, and scars.

Duodenogastric reflux in a hiatal hernia seen as retrocardiac activity on 99mTc-tetrofosmin cardiac SPECT raw-data images.

We present a patient with a large hiatal hernia resulting in duodenogastric reflux that was seen as abnormal activity below and behind the heart (retrocardiac) on SPECT images and on (99m)Tc-tetrofosmin cardiac SPECT raw-data projection images. Incidental findings such as extra- and retrocardiac activity in the thorax and abdomen should be included on all comprehensive cardiac SPECT reports.