Information processing apparatus, information processing method, and program
Provided are an information processing apparatus, an information processing method, and a program capable of accumulating appropriate relearning data. An information processing apparatus includes an input unit that inputs input data to a learned model acquired in advance through machine learning using learning data, an acquisition unit that acquires output data output from the learned model through the input using the input unit, a reception unit that receives correction performed by a user for the output data acquired by the acquisition unit, and a storage controller that performs control for storing, as relearning data of the learned model, the input data and the output data that reflects the correction received by the reception unit in a storage unit in a case where a value indicating a correction amount acquired by performing the correction for the output data is equal to or greater than a threshold value.
1. An information processing apparatus comprising:
a memory; and
a processor, coupled to the memory and configured to:
input data into a learned model, wherein the learned model is a machine learning model trained in advance on learning data and wherein the data is medical image data;
acquire output data from the learned model through inputting the data,
wherein the output data includes a portion extracted from the input data,
wherein the portion extracted from the input data is a region extracted from the medical image data;
receive correction performed by a user for the acquired output data to generate a corrected output data including an added portion that is added to the extracted portion of the output data and a deleted portion that is deleted from the extracted portion of the output data;
store, as relearning data of the learned model, the input data and the corrected output data in the memory in a case where a value indicating a correction amount acquired by performing the correction for the output data is equal to or greater than a threshold value,
wherein the value indicating the correction amount is a sum of an absolute value of a ratio of the added portion to the extracted portion and an absolute value of a ratio of the deleted portion to the extracted portion; and
retrain the learned model by using the stored relearning data.
2. The information processing apparatus according to claim 1 ,
wherein the input data is image data indicating a medical image, and
the portion extracted from the input data is a region extracted from the image data.
3. The information processing apparatus according to claim 2 ,
wherein the value indicating the correction amount is a ratio of a sum of an area of the added portion and an area of the deleted portion through the received correction performed by the user to an area of the region indicated by the output data.
4. The information processing apparatus according to claim 2 ,
wherein the value indicating the correction amount is a ratio of a sum of a volume of the added portion and a volume of the deleted portion through the correction performed by the user to a volume of the region indicated by the output data.
5. The information processing apparatus according to claim 1 ,
wherein the output data is a sentence of a medical diagnostic report.
6. The information processing apparatus according to claim 1 ,
wherein the value indicating the correction amount is the number of times the correction is performed by the user for the output data.
7. The information processing apparatus according to claim 1 ,
wherein the threshold value is selected based on a skill level of the user prior to the generation of relearning data.
8. The information processing apparatus according to claim 1 ,
wherein the threshold value is a value determined depending on a treatment plan of a subject.
9. The information processing apparatus according to claim 1 ,
wherein the threshold value is 10%.
10. An information processing method, executed by a computer, comprising:
inputting data into a learned model, wherein the learned model is a machine learning model trained in advance on learning data and wherein the data is medical image data;
acquiring output data from the learned model through inputting the data, wherein the output data includes a portion extracted from the input data, wherein the portion extracted from the input data is a region extracted from the medical image data;
receiving correction performed by a user for the acquired output data to generate a corrected output data including an added portion that is added to the extracted portion of the output data and a deleted portion that is deleted from the extracted portion of the output data;
storing, as relearning data of the learned model, the input data and the corrected output data in the memory in a case where a value indicating a correction amount acquired by performing the correction for the output data is equal to or greater than a threshold value,
wherein the value indicating the correction amount is a sum of an absolute value of a ratio of the added portion to the extracted portion and an absolute value of a ratio of the deleted portion to the extracted portion; and
retraining the learned model by using the stored relearning data.
11. An non-transitory computer readable medium storing a program causing a computer to execute a process comprising:
inputting data into a learned model, wherein the learned model is a machine learning model trained in advance on learning data and wherein the data is medical image data;
acquiring output data from the learned model through inputting the data, wherein the output data includes a portion extracted from the input data, wherein the portion extracted from the input data is a region extracted from the medical image data;
receiving correction performed by a user for the acquired output data to generate a corrected output data including an added portion that is added to the extracted portion of the output data and a deleted portion that is deleted from the extracted portion of the output data;
storing, as relearning data of the learned model, the input data and the corrected output data in the memory in a case where a value indicating a correction amount acquired by performing the correction for the output data is equal to or greater than a threshold value,
wherein the value indicating the correction amount is a sum of an absolute value of a ratio of the added portion to the extracted portion and an absolute value of a ratio of the deleted portion to the extracted portion; and
retraining the learned model by using the stored relearning data.