A deep learning model was developed to detect intracranial hemorrhage in computed tomography scans without medical annotation.
A paper presented at the Radiological Society of North America (RSNA) 2021 Annual Meeting describes a deep learning model that was developed to successfully detect intracranial hemorrhage in computed tomography (CT) scans without medical annotation.
“This method is faster because it removes the need for medical annotation, which can be added later on image errors to improve the model,” the authors wrote. “By detecting 96.6% of the normal exams, we can speed up doctor’s work, providing more time for the analysis of the slices with bleeding, increasing the precision of the diagnosis.”
Intracranial hemorrhage is a life-threatening condition that is diagnosed via CT scans. Deep learning algorithms developed to aid in the detection of bleeding within the intracranial cavity require a physician to annotate exams per slice. In this work, the researchers annotated a dataset of head CT exams using natural language processing (NLP) and applied an architecture using convolutional and recurrent neural networks to classify each exam.
A total of 8432 head CT exams collected from six hospitals and five specialized outpatient clinics were assembled and the axial volumetric unenhanced series of scans were selected. The labels were extracted from the written reports using a previously trained NLP model. Almost 40% of exams had an intracranial hemorrhage, which were not separated by bleeding subtype. Each exam was processed using brain, blood and bone windows, resliced to 25 images. A MobileNet network pre-trained with ImageNet weights was combined with a Long short-term memory (LSTM) with categorical cross-entropy as loss function. The model’s output was as follows: hemorrhage, no finding and other pathologies.
The model improved the classification without the need for a per slice annotation. On the validation set, an area under the curve (AUC) of 0.96, 0.87 for recall and 0.97 for precision was achieved. While on an external set, validated by a doctor, the AUC was 0.91, 0.85 and 0.86, respectively.
The researchers also highlighted slices where the hemorrhage appears to aid diagnosis by applying Gradient Class Activation Map (GradCAM) technique.
“Through the GradCAM method, we selected the best slices of each exam, and doctors were able to evaluate the results and indicate with more precision where a hemorrhage was found,” the authors wrote. “The identification of the most relevant slices, using the GradCAM technique, alongside clinical information, may help doctors better understand each patient case, accelerating and improving the diagnosis.”
For more coverage of RSNA 2021, click here.
SNMMI: Botox May Facilitate Relief from Dry Mouth Side Effect of PSMA-Targeted Radiopharmaceuticals
June 25th 2025For patients being treated with radiopharmaceutical agents for metastatic prostate cancer, the combination of botulinum toxin and an anti-nausea patch led to a 30 percent reduction in PSMA uptake in the salivary glands, according to preliminary research findings presented at the SNMMI conference.
Could an Emerging PET Tracer be a Game Changer for Detecting Hepatocellular Carcinoma?
June 23rd 2025In addition to over 90 percent sensitivity in detecting hepatocellular carcinoma (HCC), the glypican-3 (GPC3) targeted PET tracer 68Ga-aGPC3-scFv appeared to be advantageous in identifying HCC tumors smaller than one centimeter, according to pilot study findings presented at the SNMMI conference.
SNMMI: What a New Meta-Analysis Reveals About Radiotracers for PET/CT Detection of PCa
June 22nd 2025While (68Ga)Ga-PSMA-11 offers a pooled sensitivity rate of 92 percent for prostate cancer, (18F)-based radiotracers may offer enhanced lesion detection as well as improved imaging flexibility, according to a meta-analysis presented at the Society for Nuclear Medicine and Molecular Imaging (SNMMI) conference.
SNMMI: Can Multimodal Monitoring Bolster Outcomes with Pluvicto in Treating mCRPC?
June 22nd 2025Multimodal treatment monitoring, including SPECT/CT exams 24 hours after treatment with Lu-177 PSMA-617, may have facilitated significantly shorter therapy durations and reduced side effects in patients with mCRPC, according to a two-year study presented at the Society for Nuclear Medicine and Molecular Imaging (SNMMI) conference.